Harnessing artificial intelligence for prostate cancer management

Zhu, Lingxuan; Pan, Jiahua; Mou, Weiming; Deng, Longxin; Zhu, Yinjie; Wang, Yanqing; Pareek, Gyan; Hyams, Elias; Carneiro, Benedito A.; Hadfield, Matthew J.; El-Deiry, Wafik S.; Yang, Tao; Tan, Tao; Tong, Tong; Ta, Na; Zhu, Yan; Gao, Yisha; Lai, Yancheng; Cheng, Liang; Chen, Rui; Xue, Wei

doi:10.1016/j.xcrm.2024.101506

Cited by 5 publications

(2 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Construction of PCa-related ontologies would be a possible and feasible way to provide a systematical framework for decoding the large amounts of PCa data and knowledge, and this will contribute to the development of data sharing and integration for model analyses (152). Finally, the interpretability of AI needs to be improved continually, and clinical urologists and pathologists should strengthen their professional behaviors to avoid the biases of missed diagnosis caused by AI models (153). Translational perspectives for CRPC precision medicine and personalized therapy.…”

Section: Translational Perspectives Toward Crpc Holistic Healthcarementioning

confidence: 99%

Molecular landscape for risk prediction and personalized therapeutics of castration-resistant prostate cancer: at a glance

Jian,

Wang,

Zhang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

Prostate cancer (PCa) is commonly occurred with high incidence in men worldwide, and many patients will be eventually suffered from the dilemma of castration-resistance with the time of disease progression. Castration-resistant PCa (CRPC) is an advanced subtype of PCa with heterogeneous carcinogenesis, resulting in poor prognosis and difficulties in therapy. Currently, disorders in androgen receptor (AR)-related signaling are widely acknowledged as the leading cause of CRPC development, and some non-AR-based strategies are also proposed for CRPC clinical analyses. The initiation of CRPC is a consequence of abnormal interaction and regulation among molecules and pathways at multi-biological levels. In this study, CRPC-associated genes, RNAs, proteins, and metabolites were manually collected and integrated by a comprehensive literature review, and they were functionally classified and compared based on the role during CRPC evolution, i.e., drivers, suppressors, and biomarkers, etc. Finally, translational perspectives for data-driven and artificial intelligence-powered CRPC systems biology analysis were discussed to highlight the significance of novel molecule-based approaches for CRPC precision medicine and holistic healthcare.

show abstract

Section: Translational Perspectives Toward Crpc Holistic Healthcarementioning

confidence: 99%

Molecular landscape for risk prediction and personalized therapeutics of castration-resistant prostate cancer: at a glance

Jian,

Wang,

Zhang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…These AI-based tools have demonstrated potential in enhancing the efficiency and precision of radiologists by streamlining or enhancing human workflow. Likewise, longstanding challenges in PCa histopathology, such as limited interobserver and intraobserver agreement in measurements and Gleason grading, are being addressed through the integration of these innovative techniques (20)(21)(22)(23).…”

mentioning

confidence: 99%

Editorial: PET/CT and MRI in prostate cancer

Grizzi,

Taverna

2024

Front. Oncol.

View full text Add to dashboard Cite

Editorial on the Research Topic PET/CT and MRI in prostate cancerProstate cancer (PCa) represents one of the leading causes of cancer-related mortality (1). Age, African ancestry, and a family history of PCa are widely recognized as established risk factors (2). PCa exhibits a wide spectrum of aggressiveness, ranging from slow-growing to highly life-threatening. Large-scale trials have demonstrated that low-grade PCa (grade group 1) is associated with a very low risk of cancer-specific death. On the other hand, cancers classified in grade groups 3 through 5 display significantly higher metastatic potential and accounted for the majority of the estimated deaths from PCa (3). This diversity in the lethality of different PCa subtypes underscores the critical need for precise and accurate diagnosis of PCa. At diagnosis, 13% of PCa patients will have regional lymph node involvement and 8% will have distant metastasis (4). The most common site of metastatic PCa (mPCa) involvement is the bone, accounting for up to 90% of mPCa. Visceral organ involvement, such as in the lung, liver, adrenal gland, and brain, is less common. When compared to localized PCa, the 5-year survival rate of mPCa declines significantly from 100% to 34.1%. Early detection of mPCa is crucial for treatment. The U.S. Food and Drug Administration (FDA) sanctioned the assessment of prostate-specific antigen (PSA), a protein discharged by both healthy and cancerous prostate cells, in 1986 (5). Initially authorized for tracking patients with confirmed PCa, it was later endorsed in 1994 to assist in detecting PCa alongside digital rectal examination (DRE) in individuals aged 50 and above. Recently, screening for PCa using serum PSA has come under considerable criticism due to several trials demonstrating that using PSA serum levels often leads to overdiagnosis and overtreatment, as well as the inability to accurately differentiate between low-, intermediate-, and high-risk aggressive disease. PCa diagnosis is currently based on the gold standard invasive procedure of transrectal ultrasound (TRUS)guided needle biopsy of the prostate. The diagnostic biopsy is informed by the combination of any of the following: elevated PSA serum levels, PSA kinetics, abnormal DRE, family history, race, or abnormal previous biopsy. Gleason score, cancer stage, and cancer core information are all obtained from biopsy, and frequent or periodic biopsies are not amenable for patients. Individuals with elevated PSA levels upon screening have the option to pursue additional examinations to determine the necessity for biopsy, multiparametric magnetic resonance imaging (MRI) to pinpoint biopsy sites, or both. Those diagnosed with low-risk or favorable intermediate-risk PCa may opt for active surveillance, involving periodic PSA tests and biopsies, instead of immediate curative Frontiers in Oncology frontiersin.org 01

show abstract